arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.04151cs.CL
收藏

多任务序列标注学习的实证研究

Multi-Task Learning for Sequence Tagging: An Empirical Study

University of Southern California(南加州大学)

Soravit Changpinyo, Hexiang Hu, Fei Sha

摘要:

我们研究了三种通用的多任务学习(MTL)方法对11个序列标记任务。我们广泛的实证结果表明,在大约50%的情况下,联合学习所有11个任务提高了独立或成对学习的任务。我们还表明,成对MTL可以告诉我们什么任务可以使他人受益,或者什么任务可以受益,如果他们共同学习。特别是,我们确定了总是能使他人受益的任务,以及总是能被他人伤害的任务。有趣的是,我们的MTL方法之一产生嵌入的任务,揭示了语义和句法任务的自然聚类。我们的调查已经为在NLP中进一步利用MTL打开了大门。

英文摘要:

We study three general multi-task learning (MTL) approaches on 11 sequence tagging tasks. Our extensive empirical results show that in about 50% of the cases, jointly learning all 11 tasks improves upon either independent or pairwise learning of the tasks. We also show that pairwise MTL can inform us what tasks can benefit others or what tasks can be benefited if they are learned jointly. In particular, we identify tasks that can always benefit others as well as tasks that can always be harmed by others. Interestingly, one of our MTL approaches yields embeddings of the tasks that reveal the natural clustering of semantic and syntactic tasks. Our inquiries have opened the doors to further utilization of MTL in NLP.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑